Triple

T6677536
Position Surface form Disambiguated ID Type / Status
Subject Mel Tillis E151890 entity
Predicate child P120 FINISHED
Object Connie Tillis
Connie Tillis is a daughter of the late American country music singer and songwriter Mel Tillis.
 E611479 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Connie Tillis | Statement: [Mel Tillis, child, Connie Tillis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Connie Tillis
Context triple: [Mel Tillis, child, Connie Tillis]
  • A. Ken Loeffler
    Ken Loeffler was an American basketball coach best known for leading La Salle University to national prominence in the 1950s and for his successful stints in both college and professional basketball.
  • B. Blanche Lincoln
    Blanche Lincoln is an American Democratic politician who served as a U.S. Senator from Arkansas from 1999 to 2011.
  • C. Marta Heflin
    Marta Heflin was an American actress best known for her roles in several of Robert Altman’s ensemble films during the 1970s and 1980s.
  • D. Kelly Loeffler
    Kelly Loeffler is an American businesswoman and Republican politician who briefly served as a U.S. Senator from Georgia after being appointed to the seat in 2019.
  • E. Paula Newsome
    Paula Newsome is an American actress known for her work in television and film, including prominent roles in series like "CSI: Vegas" and "Barry."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Connie Tillis
Triple: [Mel Tillis, child, Connie Tillis]
Generated description
Connie Tillis is a daughter of the late American country music singer and songwriter Mel Tillis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Connie Tillis
Target entity description: Connie Tillis is a daughter of the late American country music singer and songwriter Mel Tillis.
  • A. Ken Loeffler
    Ken Loeffler was an American basketball coach best known for leading La Salle University to national prominence in the 1950s and for his successful stints in both college and professional basketball.
  • B. Blanche Lincoln
    Blanche Lincoln is an American Democratic politician who served as a U.S. Senator from Arkansas from 1999 to 2011.
  • C. Marta Heflin
    Marta Heflin was an American actress best known for her roles in several of Robert Altman’s ensemble films during the 1970s and 1980s.
  • D. Kelly Loeffler
    Kelly Loeffler is an American businesswoman and Republican politician who briefly served as a U.S. Senator from Georgia after being appointed to the seat in 2019.
  • E. Paula Newsome
    Paula Newsome is an American actress known for her work in television and film, including prominent roles in series like "CSI: Vegas" and "Barry."
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c687f830bc81909eb8b04dbb8450b1 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0f53af48190b0b25b61c3531158 completed March 27, 2026, 4:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7a78ab081909d904e4468293957 completed March 27, 2026, 9:33 p.m.
NEDg Description generation batch_69c6f8453af88190b237c249bfbb4f8c completed March 27, 2026, 9:36 p.m.
NED2 Entity disambiguation (via description) batch_69c6f8d5630c8190913e8572a70b82c1 completed March 27, 2026, 9:38 p.m.
Created at: March 27, 2026, 2:03 p.m.